Midjourney releases Niji v7 & an interview with Google

· Source: Visually AI by Heather Cooper · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation · Depth: Intermediate, medium

Summary

Midjourney has officially launched Niji v7, an anime-focused AI model developed over 18 months, featuring significant advancements in coherence, prompt understanding, text rendering, and --sref performance. Niji v7 emphasizes a "flatter" aesthetic, moving away from 3D-rendered looks to highlight anime linework. Users can activate it by adding "--niji 7" to prompts or selecting it in the web interface; existing V7 --sref codes are compatible, and new ones can be generated. While --cref is not supported, future updates include personalization and moodboard features. Additionally, Google's Flow team discussed enhancing AI video generation with specific verbs, and Apple and Google announced a multi-year collaboration to base future Apple Foundation Models on Google's Gemini models and cloud technology. Freepik's prompt editor was also highlighted as a useful tool for prompt refinement.

Key takeaway

For AI artists and designers focused on anime or stylized content, Niji v7 offers enhanced control and fidelity, making precise character designs and consistent styles more achievable. You should embrace highly specific prompting to fully leverage its improved prompt understanding and "flatter" aesthetic. Consider integrating Freepik's prompt editor into your workflow to refine your inputs and maximize output quality, especially for detailed anime or manga creations.

Key insights

Midjourney's Niji v7 enhances anime AI generation with improved coherence, prompt understanding, and a distinct flatter aesthetic.

Principles

Method

Activate Niji v7 by appending "--niji 7" to prompts or selecting it in the web UI. Generate new --sref styles by including "--niji 7" in the prompt for style creation.

In practice

Topics

Best for: AI Engineer, Machine Learning Engineer, Computer Vision Engineer, Prompt Engineer, Creative Technologist, AI Product Manager

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Visually AI by Heather Cooper.